Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 375 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5356. Min Range: -0.5356

Max Act: 0.5313. Min Act: -0.0000

Data Index: 58915 (C4 (Web Text))

Max Activating Token Index: 101

Text #1

Max Range: 0.5356. Min Range: -0.5356

Max Act: 0.5356. Min Act: -0.0000

Data Index: 465587 (C4 (Web Text))

Max Activating Token Index: 631

Text #2

Max Range: 0.5356. Min Range: -0.5356

Max Act: 0.5265. Min Act: -0.0000

Data Index: 1131325 (C4 (Web Text))

Max Activating Token Index: 173

Text #3

Max Range: 0.5356. Min Range: -0.5356

Max Act: 0.5087. Min Act: -0.0000

Data Index: 1084595 (C4 (Web Text))

Max Activating Token Index: 369

Text #4

Max Range: 0.5356. Min Range: -0.5356

Max Act: 0.4923. Min Act: -0.0000

Data Index: 1154954 (C4 (Web Text))

Max Activating Token Index: 189

Text #5

Max Range: 0.5356. Min Range: -0.5356

Max Act: 0.4756. Min Act: -0.0000

Data Index: 772850 (C4 (Web Text))

Max Activating Token Index: 638

Text #6

Max Range: 0.5356. Min Range: -0.5356

Max Act: 0.4701. Min Act: -0.0000

Data Index: 128799 (C4 (Web Text))

Max Activating Token Index: 593

Text #7

Max Range: 0.5356. Min Range: -0.5356

Max Act: 0.4780. Min Act: -0.0000

Data Index: 135039 (C4 (Web Text))

Max Activating Token Index: 245

Text #8

Max Range: 0.5356. Min Range: -0.5356

Max Act: 0.4415. Min Act: -0.0000

Data Index: 185896 (C4 (Web Text))

Max Activating Token Index: 307

Text #9

Max Range: 0.5356. Min Range: -0.5356

Max Act: 0.4376. Min Act: -0.0000

Data Index: 1032334 (C4 (Web Text))

Max Activating Token Index: 86

Text #10

Max Range: 0.5356. Min Range: -0.5356

Max Act: 0.4289. Min Act: -0.0000

Data Index: 4451 (C4 (Web Text))

Max Activating Token Index: 696

Text #11

Max Range: 0.5356. Min Range: -0.5356

Max Act: 0.4305. Min Act: -0.0000

Data Index: 1289782 (C4 (Web Text))

Max Activating Token Index: 179

Text #12

Max Range: 0.5356. Min Range: -0.5356

Max Act: 0.4334. Min Act: -0.0000

Data Index: 1325666 (C4 (Web Text))

Max Activating Token Index: 385

Text #13

Max Range: 0.5356. Min Range: -0.5356

Max Act: 0.4319. Min Act: -0.0000

Data Index: 58704 (C4 (Web Text))

Max Activating Token Index: 425

Text #14

Max Range: 0.5356. Min Range: -0.5356

Max Act: 0.4120. Min Act: -0.0000

Data Index: 1206780 (C4 (Web Text))

Max Activating Token Index: 55

Text #15

Max Range: 0.5356. Min Range: -0.5356

Max Act: 0.4099. Min Act: -0.0000

Data Index: 17994 (C4 (Web Text))

Max Activating Token Index: 994

Text #16

Max Range: 0.5356. Min Range: -0.5356

Max Act: 0.4097. Min Act: -0.0000

Data Index: 1025390 (C4 (Web Text))

Max Activating Token Index: 691

Text #17

Max Range: 0.5356. Min Range: -0.5356

Max Act: 0.3946. Min Act: -0.0000

Data Index: 854666 (C4 (Web Text))

Max Activating Token Index: 186

Text #18

Max Range: 0.5356. Min Range: -0.5356

Max Act: 0.4206. Min Act: -0.0000

Data Index: 870996 (C4 (Web Text))

Max Activating Token Index: 359

Text #19

Max Range: 0.5356. Min Range: -0.5356

Max Act: 0.4071. Min Act: -0.0000

Data Index: 408870 (C4 (Web Text))

Max Activating Token Index: 724